homepage

You cannot reliably use Unicode in Python identifiers because of the narrow/wide build issue. The enclosed file is fine on wide builds but gets compiler errors on narrow ones during compilation.
Go, Ruby, Java, and Perl all handle this situation without any problem; only Python has the bug.

Ouch!
Do the rejected characters qualify as identifier characters as defined in Reference 2.3 Identifiers and keywords?
http://docs.python.org/py3k/reference/lexical_analysis.html#identifiers
If some interpreter version accepts extra characters, beyond the definition (as happened in 2.x), it is not a bug for for another version to only accept what is defined.
Side question: That section has "A non-normative HTML file listing all valid identifier characters for Unicode 4.1 can be found at http://www.dcl.hpi.uni-potsdam.de/home/loewis/table-3131.html." Is the set of identifier characters now larger, and if so, has the table been enlarged?

"Terry J. Reedy" <report@bugs.python.org> wrote
 on 2011年8月12日 23:05:27 -0000: 
> Ouch!
> Do the rejected characters qualify as identifier characters as defined
> in Reference 2.3 Identifiers and keywords?
> http://docs.python.org/py3k/reference/lexical_analysis.html#identifiers
Yes, that's right, they do. You're using the standard IDS and IDC, and
XIDS and XIDC, definitions. Here were the three identifiers that were
a problem:
 Unicode = "super"
 𐐔𐐯𐑅𐐨𐑉𐐯𐐻 = "Deseret"
 𐌰𐍄𐍄𐌰‿𐌿𐌽𐍃𐌰𐍂 = "Gothic our father"
If you cannot read those, then when piped through `uniquote -v` they are:
 \N{MATHEMATICAL FRAKTUR CAPITAL U}\N{MATHEMATICAL FRAKTUR SMALL N}\N{MATHEMATICAL FRAKTUR SMALL I}\N{MATHEMATICAL FRAKTUR SMALL C}\N{MATHEMATICAL FRAKTUR SMALL O}\N{MATHEMATICAL FRAKTUR SMALL D}\N{MATHEMATICAL FRAKTUR SMALL E} = "super"
 \N{DESERET CAPITAL LETTER DEE}\N{DESERET SMALL LETTER SHORT E}\N{DESERET SMALL LETTER ES}\N{DESERET SMALL LETTER LONG I}\N{DESERET SMALL LETTER ER}\N{DESERET SMALL LETTER SHORT E}\N{DESERET SMALL LETTER TEE} = "Deseret"
 \N{GOTHIC LETTER AHSA}\N{GOTHIC LETTER TEIWS}\N{GOTHIC LETTER TEIWS}\N{GOTHIC LETTER AHSA}\N{UNDERTIE}\N{GOTHIC LETTER URUS}\N{GOTHIC LETTER NAUTHS}\N{GOTHIC LETTER SAUIL}\N{GOTHIC LETTER AHSA}\N{GOTHIC LETTER RAIDA} = "Gothic our father"
I'm not sure whether you recognize the scripts they belong to, but they're
all in the astral planes. Using `uniquote -x` on them shows:
 \x{1D518}\x{1D52B}\x{1D526}\x{1D520}\x{1D52C}\x{1D521}\x{1D522} = "super"
 \x{10414}\x{1042F}\x{10445}\x{10428}\x{10449}\x{1042F}\x{1043B} = "Deseret"
 \x{10330}\x{10344}\x{10344}\x{10330}\x{203F}\x{1033F}\x{1033D}\x{10343}\x{10330}\x{10342} = "Gothic our father"
As to whether they're proper identifiers per your reference above, I
will take the first letter from each of Unicode, 𐐔𐐯𐑅𐐨𐑉𐐯𐐻, and 𐌰𐍄𐍄𐌰‿𐌿𐌽𐍃𐌰𐍂, 
which are repsectively U, 𐐔, and 𐌰, or
 MATHEMATICAL FRAKTUR CAPITAL U
 DESERET CAPITAL LETTER DEE
 GOTHIC LETTER AHSA
or 
 1D518
 10414
 10330
and show you their full Unicode properties of these reject code points.
This requires the uniprops command, given which, these three commands 
are then completely identical:
 % uniprops -ga "U" "𐐔" "𐌰"
 % uniprops -ga 1D518 10414 10330
 % uniprops -ga "MATHEMATICAL FRAKTUR CAPITAL U" "DESERET CAPITAL LETTER DEE" "GOTHIC LETTER AHSA"
and produce this output:
U+1D518 ‹U› \N{MATHEMATICAL FRAKTUR CAPITAL U}
 \w \pL \p{LC} \p{L_} \p{L&} \p{Lu}
 All Any Alnum Alpha Alphabetic Assigned InMathematicalAlphanumericSymbols Cased Cased_Letter LC Changes_When_NFKC_Casefolded
 CWKCF Common Zyyy Lu L Gr_Base Grapheme_Base Graph GrBase ID_Continue IDC ID_Start IDS Letter L_ Uppercase_Letter Math
 Mathematical_Alphanumeric_Symbols Print Upper Uppercase Word XID_Continue XIDC XID_Start XIDS X_POSIX_Alnum X_POSIX_Alpha
 X_POSIX_Graph X_POSIX_Print X_POSIX_Upper X_POSIX_Word
 Age=3.1 Bidi_Class=L Bidi_Class=Left_To_Right BC=L Block=Mathematical_Alphanumeric_Symbols Canonical_Combining_Class=0
 Canonical_Combining_Class=Not_Reordered CCC=NR Canonical_Combining_Class=NR General_Category=Cased_Letter Script=Common
 Decomposition_Type=Font DT=Font Decomposition_Type=Non_Canon Decomposition_Type=Non_Canonical DT=NonCanon
 East_Asian_Width=Neutral GC=LC General_Category=L General_Category=Letter General_Category=L_ General_Category=LC GC=L
 General_Category=Lu General_Category=Uppercase_Letter GC=Lu Grapheme_Cluster_Break=Other GCB=XX Grapheme_Cluster_Break=XX
 Hangul_Syllable_Type=NA Hangul_Syllable_Type=Not_Applicable HST=NA Joining_Group=No_Joining_Group JG=NoJoiningGroup
 Joining_Type=Non_Joining JT=U Joining_Type=U Line_Break=AL Line_Break=Alphabetic LB=AL Numeric_Type=None NT=None
 Numeric_Value=NaN NV=NaN Present_In=3.1 IN=3.1 Present_In=3.2 IN=3.2 Present_In=4.0 IN=4.0 Present_In=4.1 IN=4.1
 Present_In=5.0 IN=5.0 Present_In=5.1 IN=5.1 Present_In=5.2 IN=5.2 Present_In=6.0 IN=6.0 SC=Zyyy Script=Zyyy
 Sentence_Break=UP Sentence_Break=Upper SB=UP Word_Break=ALetter WB=LE Word_Break=LE _X_Begin
U+10414 ‹𐐔› \N{DESERET CAPITAL LETTER DEE}
 \w \pL \p{LC} \p{L_} \p{L&} \p{Lu}
 All Any Alnum Alpha Alphabetic Assigned InDeseret Cased Cased_Letter LC Changes_When_Casefolded CWCF Changes_When_Casemapped
 CWCM Changes_When_Lowercased CWL Changes_When_NFKC_Casefolded CWKCF Deseret Dsrt Lu L Gr_Base Grapheme_Base Graph GrBase
 ID_Continue IDC ID_Start IDS Letter L_ Uppercase_Letter Print Upper Uppercase Word XID_Continue XIDC XID_Start XIDS
 X_POSIX_Alnum X_POSIX_Alpha X_POSIX_Graph X_POSIX_Print X_POSIX_Upper X_POSIX_Word
 Age=3.1 Bidi_Class=L Bidi_Class=Left_To_Right BC=L Block=Deseret Canonical_Combining_Class=0
 Canonical_Combining_Class=Not_Reordered CCC=NR Canonical_Combining_Class=NR General_Category=Cased_Letter
 Decomposition_Type=None DT=None Script=Deseret East_Asian_Width=Neutral GC=LC General_Category=L General_Category=Letter
 General_Category=L_ General_Category=LC GC=L General_Category=Lu General_Category=Uppercase_Letter GC=Lu
 Grapheme_Cluster_Break=Other GCB=XX Grapheme_Cluster_Break=XX Hangul_Syllable_Type=NA Hangul_Syllable_Type=Not_Applicable
 HST=NA Joining_Group=No_Joining_Group JG=NoJoiningGroup Joining_Type=Non_Joining JT=U Joining_Type=U Line_Break=AL
 Line_Break=Alphabetic LB=AL Numeric_Type=None NT=None Numeric_Value=NaN NV=NaN Present_In=3.1 IN=3.1 Present_In=3.2 IN=3.2
 Present_In=4.0 IN=4.0 Present_In=4.1 IN=4.1 Present_In=5.0 IN=5.0 Present_In=5.1 IN=5.1 Present_In=5.2 IN=5.2
 Present_In=6.0 IN=6.0 SC=Dsrt Script=Dsrt Sentence_Break=UP Sentence_Break=Upper SB=UP Word_Break=ALetter WB=LE
 Word_Break=LE _X_Begin
U+10330 ‹𐌰› \N{GOTHIC LETTER AHSA}
 \w \pL \p{L_} \p{Lo}
 All Any Alnum Alpha Alphabetic Assigned InGothic Gothic Is_Gothic L Lo Goth Gr_Base Grapheme_Base Graph GrBase ID_Continue
 IDC ID_Start IDS Letter L_ Other_Letter Print Word XID_Continue XIDC XID_Start XIDS X_POSIX_Alnum X_POSIX_Alpha
 X_POSIX_Graph X_POSIX_Print X_POSIX_Word
 Age=3.1 Bidi_Class=L Bidi_Class=Left_To_Right BC=L Block=Gothic Canonical_Combining_Class=0
 Canonical_Combining_Class=Not_Reordered CCC=NR Canonical_Combining_Class=NR Decomposition_Type=None DT=None
 East_Asian_Width=Neutral General_Category=L General_Category=Letter General_Category=L_ GC=L General_Category=Lo
 General_Category=Other_Letter GC=Lo Script=Gothic Grapheme_Cluster_Break=Other GCB=XX Grapheme_Cluster_Break=XX
 Hangul_Syllable_Type=NA Hangul_Syllable_Type=Not_Applicable HST=NA Joining_Group=No_Joining_Group JG=NoJoiningGroup
 Joining_Type=Non_Joining JT=U Joining_Type=U Line_Break=AL Line_Break=Alphabetic LB=AL Numeric_Type=None NT=None
 Numeric_Value=NaN NV=NaN Present_In=3.1 IN=3.1 Present_In=3.2 IN=3.2 Present_In=4.0 IN=4.0 Present_In=4.1 IN=4.1
 Present_In=5.0 IN=5.0 Present_In=5.1 IN=5.1 Present_In=5.2 IN=5.2 Present_In=6.0 IN=6.0 Script=Goth SC=Goth
 Sentence_Break=LE Sentence_Break=OLetter SB=LE Word_Break=ALetter WB=LE Word_Break=LE _X_Begin
As you see, all three are all of IDS, IDC, XIDS, and XIDC.
The reason they're failing in because on a narrow build, Python bizarrely 
splits the code points into two surrogates, and then rejects them because
surrogates aren't IDanything.
This strikes me as super crazy because you are reading from a UTF-8 source,
which therefore can handle all of Unicode. And you actually split the things
into two UTF-16 code units, too; you don't blow up just because there is
something that UCS-2 can't cope with. Indeed, I can switch things
around into literals and there is no choking:
 % cat astral-literals.python
 #!/usr/bin/env python3.2
 # -*- coding: UTF-8 -*-
 super = "Unicode" 
 Deseret = "𐐔𐐯𐑅𐐨𐑉𐐯𐐻" 
 Gothic_our_father = "𐌰𐍄𐍄𐌰‿𐌿𐌽𐍃𐌰𐍂"
 print(super)
 print(Deseret)
 print(Gothic_our_father)
because watch what happens when I run that: mirabile visu, it behaves
completely correctly despite having code points in the narrow-build-
forbidden astral planes:
 % python3.2 astral-literals.python
 Unicode
 𐐔𐐯𐑅𐐨𐑉𐐯𐐻
 𐌰𐍄𐍄𐌰‿𐌿𐌽𐍃𐌰𐍂
Again, I uniquote those for you (in case you can't read them because you
haven't gotten George Douros's free Symbola font for Unicode 6.0.0 yet from
http://users.teilar.gr/~g1951d/ . BTW, I also recommend his Alfios font for
general text, and he has several others that may be of interest):
 % python3.2 astral-literals.python | uniquote -x
 \x{1D518}\x{1D52B}\x{1D526}\x{1D520}\x{1D52C}\x{1D521}\x{1D522}
 \x{10414}\x{1042F}\x{10445}\x{10428}\x{10449}\x{1042F}\x{1043B}
 \x{10330}\x{10344}\x{10344}\x{10330}\x{203F}\x{1033F}\x{1033D}\x{10343}\x{10330}\x{10342}
 % python3.2 astral-literals.python | uniquote -v
 \N{MATHEMATICAL FRAKTUR CAPITAL U}\N{MATHEMATICAL FRAKTUR SMALL N}\N{MATHEMATICAL FRAKTUR SMALL I}\N{MATHEMATICAL FRAKTUR SMALL C}\N{MATHEMATICAL FRAKTUR SMALL O}\N{MATHEMATICAL FRAKTUR SMALL D}\N{MATHEMATICAL FRAKTUR SMALL E}
 \N{DESERET CAPITAL LETTER DEE}\N{DESERET SMALL LETTER SHORT E}\N{DESERET SMALL LETTER ES}\N{DESERET SMALL LETTER LONG I}\N{DESERET SMALL LETTER ER}\N{DESERET SMALL LETTER SHORT E}\N{DESERET SMALL LETTER TEE}
 \N{GOTHIC LETTER AHSA}\N{GOTHIC LETTER TEIWS}\N{GOTHIC LETTER TEIWS}\N{GOTHIC LETTER AHSA}\N{UNDERTIE}\N{GOTHIC LETTER URUS}\N{GOTHIC LETTER NAUTHS}\N{GOTHIC LETTER SAUIL}\N{GOTHIC LETTER AHSA}\N{GOTHIC LETTER RAIDA}
Isn't that the weirest thing? You're acting like a perfectly fine
full-unicode language even on a narrow build, and yet you reject
as identifiers those same strings that you have just faithfully
reproduced above. 
I really do not understand this. It must be a bug. Because they are
find on a wide build. And because the literals are fine even on a
narrow one.
> If some interpreter version accepts extra characters, beyond the
> definition (as happened in 2.x), it is not a bug for for another version
> to only accept what is defined.
> Side question: That section has 
>	"A non-normative HTML file listing all valid identifier characters 
> for Unicode 4.1 can be found 
> at http://www.dcl.hpi.uni-potsdam.de/home/loewis/table-3131.html ." 
Gosh that's old. Unicode *4.1*, really? I sure hope you don't rely 
on something like that to know what's what!!
> Is the set of identifier characters now larger, and if so, has the table been enlarged?
Certainly! I know this for certain science because I know that more
letters have been added. But here is the proof:
 % unichars -ua '\p{ID_Start}' | wc -l
 100747
 % unichars -ua '\p{ID_Continue}' | wc -l
 102675
Notice how Unicode has been a bit oopsy with making sure that there 
all IDS/ISC code points also have the word property:
 % unichars -ua '\w' | wc -l
 102724
I'm pretty sure a few of those are slated for "fixing", because
I've seen proposals to that effect. Here's one "letter" they 
even left out:
 % unichars -gs '\w' '\pL' '\P{IDC}'
 ⸯ U+02E2F GC=Lm SC=Common VERTICAL TILDE
That says to show me the code points which are
 word chars
 letters
 *not* IDC
Before I started poking at them, nobody ran these sort of analyses
so things could slip through. Even more annoyingly, here are non-word
characters that are indeed IDC characters:
 % unichars -gs '\W' '\p{IDC}'
 · U+000B7 GC=Po SC=Common MIDDLE DOT
 · U+00387 GC=Po SC=Common GREEK ANO TELEIA
 ፩ U+01369 GC=No SC=Ethiopic ETHIOPIC DIGIT ONE
 ፪ U+0136A GC=No SC=Ethiopic ETHIOPIC DIGIT TWO
 ፫ U+0136B GC=No SC=Ethiopic ETHIOPIC DIGIT THREE
 ፬ U+0136C GC=No SC=Ethiopic ETHIOPIC DIGIT FOUR
 ፭ U+0136D GC=No SC=Ethiopic ETHIOPIC DIGIT FIVE
 ፮ U+0136E GC=No SC=Ethiopic ETHIOPIC DIGIT SIX
 ፯ U+0136F GC=No SC=Ethiopic ETHIOPIC DIGIT SEVEN
 ፰ U+01370 GC=No SC=Ethiopic ETHIOPIC DIGIT EIGHT
 ፱ U+01371 GC=No SC=Ethiopic ETHIOPIC DIGIT NINE
 ᧚ U+019DA GC=No SC=New_Tai_Lue NEW TAI LUE THAM DIGIT ONE
 ℘ U+02118 GC=Sm SC=Common SCRIPT CAPITAL P
 ℮ U+0212E GC=So SC=Common ESTIMATED SYMBOL
 ゙ U+0309B GC=Sk SC=Common KATAKANA-HIRAGANA VOICED SOUND MARK
 ゚ U+0309C GC=Sk SC=Common KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK
Digits are supposed to be GC=Nd not GC=No, so I don't know what the story 
is there. Maybe they don't have a zero?
 % uniprops 'ETHIOPIC DIGIT ZERO'
 uniprops: no character named ‹ETHIOPIC DIGIT ZERO›
 % uniprops 'ETHIOPIC DIGIT ONE'
 U+1369 ‹፩› \N{ETHIOPIC DIGIT ONE}
 \pN \p{No}
 All Any Assigned InEthiopic Ethiopic Is_Ethiopic Ethi N No Gr_Base Grapheme_Base Graph GrBase ID_Continue IDC Number
 Other_Number Print XID_Continue XIDC X_POSIX_Graph X_POSIX_Print
I guess that's it then: you can't assemble bigendian base-10 integers 
out of digits whose set lacks a zero, which is the key criterion for GC=Nd
and for NT=De (Numeric_Type=Decimal), as in regular digits:
 % uniprops -ga 1
U+0031 ‹1› \N{DIGIT ONE}
 \w \d \pN \p{Nd}
 AHex ASCII_Hex_Digit All Any Alnum ASCII Assigned Basic_Latin Common Zyyy Decimal_Number Digit Nd N Gr_Base Grapheme_Base
 Graph GrBase Hex XDigit Hex_Digit ID_Continue IDC Number PerlWord POSIX_Alnum POSIX_Digit POSIX_Graph POSIX_Print
 POSIX_Word POSIX_XDigit Print Word XID_Continue XIDC X_POSIX_Alnum X_POSIX_Digit X_POSIX_Graph X_POSIX_Print X_POSIX_Word
 X_POSIX_XDigit
 Age=1.1 Block=Basic_Latin Bidi_Class=EN Bidi_Class=European_Number BC=EN Block=ASCII BLK=ASCII Canonical_Combining_Class=0
 Canonical_Combining_Class=Not_Reordered CCC=NR Canonical_Combining_Class=NR Script=Common General_Category=Decimal_Number
 Decomposition_Type=None DT=None East_Asian_Width=Na East_Asian_Width=Narrow EA=Na GC=Nd General_Category=Digit
 General_Category=Number General_Category=Nd Grapheme_Cluster_Break=Other GCB=XX Grapheme_Cluster_Break=XX
 Hangul_Syllable_Type=NA Hangul_Syllable_Type=Not_Applicable HST=NA Joining_Group=No_Joining_Group JG=NoJoiningGroup
 Joining_Type=Non_Joining JT=U Joining_Type=U Line_Break=NU Line_Break=Numeric LB=NU Numeric_Type=De Numeric_Type=Decimal
 NT=De Numeric_Value=1 NV=1 Present_In=1.1 IN=1.1 Present_In=2.0 IN=2.0 Present_In=2.1 IN=2.1 Present_In=3.0 IN=3.0
 Present_In=3.1 IN=3.1 Present_In=3.2 IN=3.2 Present_In=4.0 IN=4.0 Present_In=4.1 IN=4.1 Present_In=5.0 IN=5.0
 Present_In=5.1 IN=5.1 Present_In=5.2 IN=5.2 Present_In=6.0 IN=6.0 SC=Zyyy Script=Zyyy Sentence_Break=NU
 Sentence_Break=Numeric SB=NU Word_Break=NU Word_Break=Numeric WB=NU _X_Begin
But back to the mismatch between \w and IDC. Isn't that really annoying?
The first two occur in NFD, which is a pain. So you start with
something that is all \w, then you decompose it, and whammo.
This brings up a whole nother issue. Insofar as they may differ, should
one track \w or should one track IDS/IDC? It is extremely vexing,
because whatever you do, you will change the lexical texture of your
language. We recently swapped around from one to the other, and there
was one person whose module had to change. He had no idea he was even
using one of these things in an ident, and was happy to change it. But
we lucked out that time. It is terribly bothersome situation, and I do
not know what the best strategy actually is, or the safest one, nor
whether those differ. It troubles us, too, I do promise you.
One thing I might do to trouble you less...
If you don't have the uniquote, uniprops, or unichars commands yet,
and would like them, then well *those* I can tell you where to find. :)
--tom

New changeset 787ed1a7aba8 by Benjamin Peterson in branch '3.2':
in narrow builds, make sure to test codepoints as identifier characters (closes #12732)
http://hg.python.org/cpython/rev/787ed1a7aba8
New changeset 5af15f018e20 by Benjamin Peterson in branch 'default':
merge 3.2 (#12732)
http://hg.python.org/cpython/rev/5af15f018e20